Principal component analysis for assessing oil and gas production (the case of the Kogalym field)

Abstract

When analysing the criteria measuring the volume of oil deposits with wide gaps in configuration of reservoir parameters and physicochemical properties of fluid, it is necessary to group and characterize objects under study. Classification makes it possible to adjust conformity and distinctive features of deposits, and explain research theories. The analysis of information according to the subjects determined by the parameters measured or evaluated is difficult to carry out. It requires a lot of time and effort. Therefore, it is necessary to reduce the data volume, compress initial information to the smallest number of characteristics. Parameters can be selected from initial data or calculated and modified (i.e. minimum loss of data on the objects under study). The effective analysis tool capable of identifying the problems is the principal component analysis (PCA) which is a method for reducing the data volume. The principal component can be found in almost every text using the multivariate analysis.

Data Exploration Using Tableau and Principal Component Analysis

“…This simplification process is carried out by making sample projections in two-dimensional or three-dimensional axes (principal components) as a new system of variables [8]. To assess oil and gas production, PCA is one of the useful methods that has already been implemented [9], including the scaled principal component analysis (s-PCA), to improve the oil price predictability with technical indicators [10].…”